The paper introduces RobustTests, a framework that improves reinforcement learning for code generation by synthesizing test cases from faulty code and refining rewards with a dense, stepwise function. It uses validator agents and behavioral clustering to filter out invalid or redundant tests, and incorporates pass‑rate‑based rewards to counter hallucination noise. Experiments on CodeContests and LiveCodeBench show that fine‑tuning Qwen3‑32B with RobustTests yields a 3% absolute performance gain over baseline methods.
arXiv:2608. 16742v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging.
arXiv:2509. 24148v3 Announce Type: replace-cross Abstract: Test-Driven Development (TDD) is a widely adopted practice that requires developers to create and execute tests alongside implementation.
Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging. Existing approaches often use generated tests as static post-hoc validators, which limits their ability to guide implementation and may introduce misleading feedback when the tests themselves are incomplete or incorrect.
SWE-Critix is a post‑training pipeline that creates generalist verifiers for coding‑agent trajectories. It uses supervised fine‑tuning followed by reinforcement learning to train 30B models on CodeForge‑Preview data, enabling the verifier to predict completion labels and generate natural‑language explanations. The approach raises classification accuracy from 57% to 78% on a held‑out test set.
TestJack is a scalable framework that audits large language model (LLM) coding agents by generating new tests for each trial, focusing on prompt requirements that may be violated. It keeps only the tests passed by the ground‑truth patch and re‑examines failures, providing replayable evidence for each confirmed error. In experiments across six model backends and five benchmarks, TestJack found that 34.4% of trials deemed correct actually violated task requirements, reducing the overall resolution rate from 50.6% to 33.2%.
arXiv:2507. 22580v2 Announce Type: replace-cross Abstract: Automated Program Repair (APR) seeks to automatically correct software bugs without requiring human intervention.
arXiv:2602. 20213v2 Announce Type: replace-cross Abstract: The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases.
SWEPatchTest is a benchmark that evaluates software tests by measuring their ability to reproduce issues, accept correct patches, and reject incorrect ones across 619 tasks and 82,579 candidate patches. It introduces the Joint Validation Rate metric, revealing that even the best configurations only achieve 9.21% success when all three criteria are met. Using these validation scores to select demonstrations for supervised fine‑tuning can roughly triple the Joint Validation Rate and enhance downstream repair performance on multiple SWE‑bench datasets.
The paper introduces Test Cases Scaling (TCS), a two‑stage reinforcement learning framework that automatically generates sound and discriminative test cases for code large language models (LLMs). Stage 1 trains a test generator to produce tests aligned with a reference solution, while Stage 2 refines the generator to produce counterexample tests that target the solver’s current failure modes. Experiments on TACO and LiveCodeBench show that TCS improves pass@1 and inference‑time answer selection, and the learned test generator can also effectively rank outputs from other LLMs.
arXiv:2609.06229v1 Announce Type: cross Abstract: Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical...
The paper introduces Test Cases Scaling (TCS), a two‑stage reinforcement learning framework that automatically generates sound and discriminative test cases for code‑generation large language models. Stage 1 trains a test generator to produce tests aligned with a reference solution, while Stage 2 refines the generator to produce counterexample tests that target the model’s current failure modes. Experiments on TACO and LiveCodeBench show that TCS improves pass@1 and inference‑time answer selection, and the learned generator also aids in selecting better outputs from other LLMs.
arXiv:2606. 12864v1 Announce Type: cross Abstract: Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored.